Skip to content

Python

Norlen is OpenAI-compatible, so the official openai SDK in Python works by pointing base_url at Norlen.

Terminal window
pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.norlen.io/v1",
api_key="seu-token", # de preferência os.environ["NORLEN_API_KEY"]
)
resp = client.chat.completions.create(
model="qwen3.6-35b",
messages=[{"role": "user", "content": "Hello, Norlen!"}],
)
print(resp.choices[0].message.content)
stream = client.chat.completions.create(
model="qwen3.6-35b",
messages=[{"role": "user", "content": "Count to five."}],
stream=True,
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="", flush=True)
resp = client.embeddings.create(
model="qwen3-embedding",
input=["first text", "second text"],
)
print(resp.data[0].embedding[:5])

Image generation uses a different base URL (app.norlen.io/api/v1) and does not go through the SDK — use requests:

import base64, requests
r = requests.post(
"https://app.norlen.io/api/v1/images/generations",
headers={"Authorization": "Bearer SEU_TOKEN"},
json={"model": "qwen-image", "prompt": "A lighthouse at dawn", "size": "1024x1024"},
timeout=120,
)
open("imagem.png", "wb").write(base64.b64decode(r.json()["data"][0]["b64_json"]))